End of training

README.md

@@ -1,12 +1,27 @@
 ---
+language:
+- en
 license: apache-2.0
 tags:
 - generated_from_trainer
+datasets:
+- glue
 metrics:
 - accuracy
 model-index:
 - name: mobilebert_sa_GLUE_Experiment_logit_kd_data_aug_qnli
-  results: []
+  results:
+  - task:
+      name: Text Classification
+      type: text-classification
+    dataset:
+      name: GLUE QNLI
+      type: glue
+      args: qnli
+    metrics:
+    - name: Accuracy
+      type: accuracy
+      value: 0.5923485264506682
 ---
 
 <!-- This model card has been generated automatically according to the information the Trainer had access to. You
@@ -14,10 +29,10 @@ should probably proofread and complete it, then remove this comment. -->
 
 # mobilebert_sa_GLUE_Experiment_logit_kd_data_aug_qnli
 
-This model is a fine-tuned version of [google/mobilebert-uncased](https://huggingface.co/google/mobilebert-uncased) on an unknown dataset.
+This model is a fine-tuned version of [google/mobilebert-uncased](https://huggingface.co/google/mobilebert-uncased) on the GLUE QNLI dataset.
 It achieves the following results on the evaluation set:
-- Loss: 1.1662
-- Accuracy: 0.6114
+- Loss: 1.1420
+- Accuracy: 0.5923
 
 ## Model description
 

all_results.json

@@ -0,0 +1,14 @@
+{
+    "epoch": 6.0,
+    "eval_accuracy": 0.5923485264506682,
+    "eval_loss": 1.1420139074325562,
+    "eval_runtime": 12.5331,
+    "eval_samples": 5463,
+    "eval_samples_per_second": 435.885,
+    "eval_steps_per_second": 3.431,
+    "train_loss": 0.44199674663453337,
+    "train_runtime": 148025.2261,
+    "train_samples": 4250511,
+    "train_samples_per_second": 1435.739,
+    "train_steps_per_second": 11.217
+}

eval_results.json

@@ -0,0 +1,9 @@
+{
+    "epoch": 6.0,
+    "eval_accuracy": 0.5923485264506682,
+    "eval_loss": 1.1420139074325562,
+    "eval_runtime": 12.5331,
+    "eval_samples": 5463,
+    "eval_samples_per_second": 435.885,
+    "eval_steps_per_second": 3.431
+}

logs/events.out.tfevents.1675812433.serv-3332.1890546.2

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:16f1312968c168a02280493dd974f112da8df854ae3fc8ab6ffa6bba9d8402c7
+size 369

train_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 6.0,
+    "train_loss": 0.44199674663453337,
+    "train_runtime": 148025.2261,
+    "train_samples": 4250511,
+    "train_samples_per_second": 1435.739,
+    "train_steps_per_second": 11.217
+}

trainer_state.json

@@ -0,0 +1,115 @@
+{
+  "best_metric": 1.1420139074325562,
+  "best_model_checkpoint": "mobilebert_sa_GLUE_Experiment_logit_kd_data_aug_qnli/checkpoint-33208",
+  "epoch": 6.0,
+  "global_step": 199248,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "learning_rate": 4.9e-05,
+      "loss": 0.6899,
+      "step": 33208
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.5923485264506682,
+      "eval_loss": 1.1420139074325562,
+      "eval_runtime": 12.6193,
+      "eval_samples_per_second": 432.909,
+      "eval_steps_per_second": 3.407,
+      "step": 33208
+    },
+    {
+      "epoch": 2.0,
+      "learning_rate": 4.8e-05,
+      "loss": 0.498,
+      "step": 66416
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.5943620721215449,
+      "eval_loss": 1.219602346420288,
+      "eval_runtime": 12.6869,
+      "eval_samples_per_second": 430.602,
+      "eval_steps_per_second": 3.389,
+      "step": 66416
+    },
+    {
+      "epoch": 3.0,
+      "learning_rate": 4.7e-05,
+      "loss": 0.4209,
+      "step": 99624
+    },
+    {
+      "epoch": 3.0,
+      "eval_accuracy": 0.5976569650375252,
+      "eval_loss": 1.2370126247406006,
+      "eval_runtime": 12.7229,
+      "eval_samples_per_second": 429.383,
+      "eval_steps_per_second": 3.38,
+      "step": 99624
+    },
+    {
+      "epoch": 4.0,
+      "learning_rate": 4.600000000000001e-05,
+      "loss": 0.3746,
+      "step": 132832
+    },
+    {
+      "epoch": 4.0,
+      "eval_accuracy": 0.5972908658246385,
+      "eval_loss": 1.2783989906311035,
+      "eval_runtime": 12.6633,
+      "eval_samples_per_second": 431.405,
+      "eval_steps_per_second": 3.396,
+      "step": 132832
+    },
+    {
+      "epoch": 5.0,
+      "learning_rate": 4.5e-05,
+      "loss": 0.3449,
+      "step": 166040
+    },
+    {
+      "epoch": 5.0,
+      "eval_accuracy": 0.5938129233022149,
+      "eval_loss": 1.2648983001708984,
+      "eval_runtime": 12.6182,
+      "eval_samples_per_second": 432.944,
+      "eval_steps_per_second": 3.408,
+      "step": 166040
+    },
+    {
+      "epoch": 6.0,
+      "learning_rate": 4.4000000000000006e-05,
+      "loss": 0.3238,
+      "step": 199248
+    },
+    {
+      "epoch": 6.0,
+      "eval_accuracy": 0.6113856855207761,
+      "eval_loss": 1.1661865711212158,
+      "eval_runtime": 12.5606,
+      "eval_samples_per_second": 434.933,
+      "eval_steps_per_second": 3.423,
+      "step": 199248
+    },
+    {
+      "epoch": 6.0,
+      "step": 199248,
+      "total_flos": 7.996297956242227e+17,
+      "train_loss": 0.44199674663453337,
+      "train_runtime": 148025.2261,
+      "train_samples_per_second": 1435.739,
+      "train_steps_per_second": 11.217
+    }
+  ],
+  "max_steps": 1660400,
+  "num_train_epochs": 50,
+  "total_flos": 7.996297956242227e+17,
+  "trial_name": null,
+  "trial_params": null
+}